jingyaogong
|
37300329c5
|
[fix] dtype & lr
|
2025-12-09 13:01:38 +08:00 |
jingyaogong
|
7614a3bf90
|
[fix] reduce aux_loss_alpha
|
2025-12-05 23:08:29 +08:00 |
jingyaogong
|
295b9ad443
|
[feat] update yarn
|
2025-12-01 16:15:05 +08:00 |
jingyaogong
|
cafc3b22df
|
[feat] release memory
|
2025-11-27 19:39:49 +08:00 |
jingyaogong
|
21cadea5f5
|
[fix] model attn_mask
|
2025-11-19 22:26:53 +08:00 |
jingyaogong
|
7aef898647
|
[fix] update model
|
2025-11-18 13:07:20 +08:00 |
yuyu5333
|
9c29046d2e
|
fix: attn_forwad when is_causal=True assert attn_mask is None
|
2025-11-18 03:17:17 +00:00 |
jingyaogong
|
8bb98c9790
|
[fix] update model
|
2025-10-17 00:09:32 +08:00 |
jingyaogong
|
7d81a0a6f0
|
fix bugs
|
2025-04-27 09:56:49 +08:00 |
jingyaogong
|
e74843bd09
|
250426
|
2025-04-26 10:05:47 +08:00 |